Turn abandoned patents
into your own filing
into your own filing
This invention describes a computer system that learns what people like by connecting two types of information: structured facts about the world (like subject-predicate-object statements) and records of how a user interacts with the system. It links these two data sources to understand user preferences and then generates personalized recommendations, potentially explaining why a suggestion was made. The claims narrow the invention to specific methods of automatically accessing user behavior and semantic facts, and inferring user actions from their usage.
Why it matters: Filed before large language models (LLMs) and advanced knowledge graph technologies matured. These advancements now make it significantly easier and more powerful to build, link, and infer from the semantic and behavioral chains described, improving recommendation accuracy and explanation quality.
AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.
Reinvent this with AI
